DataNarrative: Automated Data-Driven Storytelling with Visualizations and Texts
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914963954597888 |
|---|---|
| author | Islam, Mohammed Saidul Laskar, Md Tahmid Rahman Parvez, Md Rizwan Hoque, Enamul Joty, Shafiq |
| author_facet | Islam, Mohammed Saidul Laskar, Md Tahmid Rahman Parvez, Md Rizwan Hoque, Enamul Joty, Shafiq |
| contents | Data-driven storytelling is a powerful method for conveying insights by combining narrative techniques with visualizations and text. These stories integrate visual aids, such as highlighted bars and lines in charts, along with textual annotations explaining insights. However, creating such stories requires a deep understanding of the data and meticulous narrative planning, often necessitating human intervention, which can be time-consuming and mentally taxing. While Large Language Models (LLMs) excel in various NLP tasks, their ability to generate coherent and comprehensive data stories remains underexplored. In this work, we introduce a novel task for data story generation and a benchmark containing 1,449 stories from diverse sources. To address the challenges of crafting coherent data stories, we propose a multiagent framework employing two LLM agents designed to replicate the human storytelling process: one for understanding and describing the data (Reflection), generating the outline, and narration, and another for verification at each intermediary step. While our agentic framework generally outperforms non-agentic counterparts in both model-based and human evaluations, the results also reveal unique challenges in data story generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_05346 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DataNarrative: Automated Data-Driven Storytelling with Visualizations and Texts Islam, Mohammed Saidul Laskar, Md Tahmid Rahman Parvez, Md Rizwan Hoque, Enamul Joty, Shafiq Computation and Language Data-driven storytelling is a powerful method for conveying insights by combining narrative techniques with visualizations and text. These stories integrate visual aids, such as highlighted bars and lines in charts, along with textual annotations explaining insights. However, creating such stories requires a deep understanding of the data and meticulous narrative planning, often necessitating human intervention, which can be time-consuming and mentally taxing. While Large Language Models (LLMs) excel in various NLP tasks, their ability to generate coherent and comprehensive data stories remains underexplored. In this work, we introduce a novel task for data story generation and a benchmark containing 1,449 stories from diverse sources. To address the challenges of crafting coherent data stories, we propose a multiagent framework employing two LLM agents designed to replicate the human storytelling process: one for understanding and describing the data (Reflection), generating the outline, and narration, and another for verification at each intermediary step. While our agentic framework generally outperforms non-agentic counterparts in both model-based and human evaluations, the results also reveal unique challenges in data story generation. |
| title | DataNarrative: Automated Data-Driven Storytelling with Visualizations and Texts |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2408.05346 |